计算机科学 ›› 2017, Vol. 44 ›› Issue (12): 292-297.doi: 10.11896/j.issn.1002-137X.2017.12.053
刘红敏,李璐,王志衡
LIU Hong-min, LI Lu and WANG Zhi-heng
摘要： 鉴于当前基于采样模型的二值描述子的采样信息相关度高且描述子的鲁棒性较低,通过改进视网膜采样模型,提出基于采样点组二值化策略的鲁棒二值描述子。首先,通过减少采样层数并增大采样点间的距离,设计出低采样点密度和低采样区域重叠度的改进视网膜采样模型。然后,在模型中的采样点圆形邻域内获取若干像素点,将其与采样点一起组成采样点组,分别计算两个采样点组对应点的灰度对比结果,并利用投票策略决定最终二值结果。最后,将采样点组的梯度对比信息与灰度对比信息一起编码生成描述子,以提高对相似灰度区域的描述力。通过对比实验可以看出,所提二值描述子对各种图像变化具有较好的鲁棒性且具有较好的匹配效果。
| [1] XIAO X,WANG X B,WANG S J.Algorithm Based on EdgePoint Feature for Image Matching [J].Journal of Chinese Computer Systems,2012,3(11):2535-2537.(in Chinese) 肖潇,王宪保,王守觉.一种边缘点特征图像配准算法[J].小型微型计算机系统,2012,3(11):2535-2537. [2] YANG X F,HUANG Y M,GAO F,et al.New corner detection algorithm of chess board image for camera calibration [J].Chinese Journal of Scientific Instrument,2011,2(5):1109-1113.(in Chinese) 杨幸芳,黄玉美,高峰,等.用于摄像机标定的棋盘图像角点检测新算法[J].仪器仪表学报,2011,2(5):1109-1113. [3] DENG J X,XIONG Z Y,ZENG D M.Face Recognition Based on Improved Fast EMD-MIL Framework and Information Fusion[J].Journal of Sichuan University (Engeering Science Edition),2012,4(2):99-104.(in Chinese) 邓剑勋,熊忠阳,曾代敏.基于EMD 的融合特征快速多示例人脸识别算法[J].四川大学学报科学(工程版),2012,4(2):99-104. [4] LIU W H,BAI B D,ZHAO X Q.Image Restoration Algorithm Based on Fusion with Fuzzy Similarity [J].Journal of Compu-ter-Aided Design & Computer Graphics,2013,5(5):616-621.(in Chinese) 刘卫华,白本督,赵小强.基于模糊相似度融合的图像复原算法[J].计算机辅助设计与图形学报,2013,5(5):616-621. [5] LOWE D G.Distinctive Image Features from Scale-invariantKeypoints [J].International Journal of Computer Vision,2004,0(2):91-110. [6] BAY H,ESS A,TUYTELAARS T,et al.SURF:Speeded Up Robust Features [J].Computer Vision and Image Understan-ding,2008,0(3):346-359. [7] HEIKKILA M,PIETIKAINEN M,SCHMID C.Description ofinterest regions with local binary patterns [J].Pattern Recognition,2009,2(3):425-436. [8] GUPTA R,PATIL H,MITTAL A.Robust order-based me-thods for feature description [C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR).2010:334-341. [9] CALONDER M,LEPETIT V,OZUYSAL M,et al.BRIEF:Computing A Local Binary Descriptor Very Fast [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,4(7):1281-1298. [10] RUBLEE E,RABAUD V,KONOLIDGE K,et al.ORB:An Efficient Alternative to SIFT or SURF [C]∥International Confe-rence on Computer Vision,2011,8(11):2564-2571. [11] LEUTENEGGER S,CHLI M,SIEGWART R.BRISK:Binary Robust Invariant Scalable Keypoints [J].International Confe-rence on Computer Vision,2011,8(11):2548-2555. [12] ALAHI A,ORTIZ R,VANDERGHEYNST P.FREAK:FastRetina Keypoint [J].IEEE Conference on Computer Vision and Pattern Recognition,2012,7(10):510-517. [13] MIKOLAJCZYK K,SCHMID C.A Performance Evaluation of Local Descriptors [J].IEEE Transactionson Pattern Analysis and Machine Intelligence,2005,7(10):1615-1630. [14] HARRIS C,STEPHENS M.A combined corner and edge detector [C]∥Proceedings of 4th Alvey Vision Conference.1988:147-151. [15] MIKOLAJCZYK K,SCHMID C.Scale & affine invariant inte-rest point detectors [J].International Journal of Computer Vision,2004,0(1):63-86. [16] ROSTEN E,DRUMMOND T.Faster and better:A Machinelearning approach to corner detection [J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2008,2(1):105-119. [17] FIELD G,GAUTHIER J,SHER A,et al.Functional connectivity in the retina at the resolution of photoreceptors[J].Naure,2010,7(7316):673-677. |
| No related articles found! |
|
||
首页